© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 13452
    Prev
    Next
    INDEX
    Explanations

    felt or salt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ر
    3.02
    특별시
    2.92
    ਰ
    2.78
     وعلى
    2.52
    ен
    2.45
    er
    2.44
    رى
    2.23
    h
    2.23
    人士
    2.20
    hhh
    2.19
    POSITIVE LOGITS
    おります
    2.89
    ுகள்
    2.20
     Seit
    2.03
    ্ৰ
    1.98
    т
    1.96
    ğ
    1.89
     descob
    1.87
    conoc
    1.87
    ৮
    1.87
    gerald
    1.84
    Activations Density 0.234%

    No Known Activations